# Safe Reinforcement Learning on Safety Gymnasium Humanoid (threshold=5)

Source: [Safe Reinforcement Learning on Safety Gymnasium Humanoid (threshold=5)](<https://www.sota2.com/research/sota/safe-reinforcement-learning-on-safety-gymnasium-humanoid-threshold-5>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-26T13:28:20.173Z

Evaluation of Safe Reinforcement Learning performance on the Safety Gymnasium Humanoid environment, specifically configured with a threshold of 5. Performance is measured by Return and Cost.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Safe Reinforcement Learning |
| Dataset (including any stated split) | Safety Gymnasium Humanoid threshold=5 |
| Metric | Return |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Return](<https://www.sota2.com/research/sota/safe-reinforcement-learning-on-safety-gymnasium-humanoid-threshold-5.md?metric=Return>): Higher is better; unit: SCALAR.

- [Cost](<https://www.sota2.com/research/sota/safe-reinforcement-learning-on-safety-gymnasium-humanoid-threshold-5.md?metric=Cost>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Return | Result date | Report paper |
| --- | --- | --- | --- |
| PPO-BT | 5948 | Not recorded | 69c4bd640636e5bf4afc7435 |
| PPO-Lag | 5876 | Not recorded | 69c4bd640636e5bf4afc7435 |
| PbCRL | 5247 | Not recorded | 69c4bd640636e5bf4afc7435 |
| RLSF | 4816 | Not recorded | 69c4bd640636e5bf4afc7435 |

### PPO-BT

Return: 5948. Result ID: 69c5345c47f34ce924aec392.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd640636e5bf4afc7435.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70e81e209131cea4ddd5.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### PPO-Lag

Return: 5876. Result ID: 69c5345c47f34ce924aec38f.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd640636e5bf4afc7435.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66761e209131cea10437.md>)

Recorded evaluation configuration: {"Type":"Oracle"}. This record does not assert independent reproduction.

### PbCRL

Return: 5247. Result ID: 69c5345c47f34ce924aec390.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd640636e5bf4afc7435.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c4bd640636e5bf4afc7435.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### RLSF

Return: 4816. Result ID: 69c5345c47f34ce924aec391.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd640636e5bf4afc7435.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76891e209131cea6d835.md>)

[Implementation](<https://github.com/shshnkreddy/RLSF>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.